MASA - a jadohu Collection

jadohu 's Collections

MASA

MASA

updated 2 days ago

Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning

jadohu/Qwen3-14B-MASA

Reinforcement Learning • 15B • Updated 3 days ago • 16 • 1
jadohu/Qwen3-14B-GRPO

Reinforcement Learning • 15B • Updated 2 days ago • 7 • 1
jadohu/Qwen3-8B-MASA

Reinforcement Learning • 8B • Updated 2 days ago • 10 • 1
jadohu/Qwen3-8B-MASA-efficient

Reinforcement Learning • 8B • Updated 2 days ago • 9 • 1
jadohu/Qwen3-8B-GRPO

Reinforcement Learning • 8B • Updated 2 days ago • 7 • 1